Skip to content

model building

2 messages · Davide Guido, Thierry Onkelinx

#
Hello Everyone!

I have a dataset with 150.000 statistical units (subjects) and 5 variables:

- Binary outcome (0/1) (y)
- municipality (string) (25 small areas)
- gender
- age
- copper concentration (in ppm) (25 level, one by municipality)

The last one, i.e. copper concentration, has been revealed per municipality 
(25 levels) and it is defined as municipalty mean of the different municipal 
sampling sites. I'm interested to the (conditional) copper effect on outcome 
and I have tried to specify this GLMM: 

gLMM <- glmer (y ~ gender + age + copper + (1 | municipality), family="
binomial", data=datiSM) 


Is it correct fit a model containing both disaggregated and aggregated 
variables? 

Unfortunately, I cannot measure the copper at disaggregated level (by 
subject). 

Thanks in advance

Davide
#
Dear Davide,

Your model formulation is OK.

Best regards,

ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek / Research Institute for Nature and
Forest
team Biometrie & Kwaliteitszorg / team Biometrics & Quality Assurance
Kliniekstraat 25
1070 Anderlecht
Belgium

To call in the statistician after the experiment is done may be no more
than asking him to perform a post-mortem examination: he may be able to say
what the experiment died of. ~ Sir Ronald Aylmer Fisher
The plural of anecdote is not data. ~ Roger Brinner
The combination of some data and an aching desire for an answer does not
ensure that a reasonable answer can be extracted from a given body of data.
~ John Tukey

2015-10-29 20:25 GMT+01:00 Davide Guido via R-sig-mixed-models <
r-sig-mixed-models at r-project.org>: